CN118409157A - High voltage leakage monitoring and fault location system for coal mining area power grid - Google Patents
High voltage leakage monitoring and fault location system for coal mining area power grid Download PDFInfo
- Publication number
- CN118409157A CN118409157A CN202410453745.7A CN202410453745A CN118409157A CN 118409157 A CN118409157 A CN 118409157A CN 202410453745 A CN202410453745 A CN 202410453745A CN 118409157 A CN118409157 A CN 118409157A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- time
- monitoring
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/52—Testing for short-circuits, leakage current or ground faults
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
本发明公开了煤矿区电网高压漏电监控及故障定位系统，涉及电力监控技术领域，本发明采用多源数据融合，采集和综合分析电力设备、环境传感器、设备运行数据，不仅依赖于电网数据，还结合其他数据源，环境传感器数据、设备运行数据，构建多维度的故障诊断模型，提高了系统诊断的准确性和全面性，同时采用深度学习LSTM模型和GRU模型，提高故障诊断的准确性和效率，能够更加精准地判断系统的异常状态，从而及时预警和处理潜在故障，此外建立实时数据反馈机制，能够对系统状态进行实时评估和调整，大大提高系统的响应速度和故障处理效率。
The invention discloses a high-voltage leakage monitoring and fault location system for a coal mining area power grid, and relates to the technical field of power monitoring. The invention adopts multi-source data fusion to collect and comprehensively analyze power equipment, environmental sensors, and equipment operation data. It not only relies on power grid data, but also combines other data sources, environmental sensor data, and equipment operation data to build a multi-dimensional fault diagnosis model, thereby improving the accuracy and comprehensiveness of system diagnosis. At the same time, deep learning LSTM models and GRU models are adopted to improve the accuracy and efficiency of fault diagnosis, and the abnormal state of the system can be judged more accurately, thereby timely warning and processing potential faults. In addition, a real-time data feedback mechanism is established, which can evaluate and adjust the system state in real time, greatly improving the response speed of the system and the efficiency of fault processing.
Description
Technical Field
The invention relates to the technical field of power monitoring, in particular to a high-voltage leakage monitoring and fault positioning system for a power grid in a coal mine area.
Background
Most of coal mines in China belong to underground mining, a coal mine power supply system sequentially comprises a ground substation, an underground central substation, a mining area substation and a mobile substation from top to bottom, a main line type power grid structure formed by multi-level short cables is commonly adopted by the power supply system, the high-voltage power supply level of the coal mine is generally 6-10 kV, the low-voltage level is 3300V, 1140V, 660V, 380V and 220V, the coal mine safety regulation requires that the underground power supply network adopts a double-loop power supply mode, two loops are standby, namely, after one loop power supply or line fails, the other loop normal power supply can be connected by adjusting a high-voltage switch, the continuous power supply of a load is ensured, the comprehensive power monitoring system of the coal mine is an electric power automation platform which is specially used for monitoring and monitoring the underground power supply system, an electric power protection device, dispatching automation and the like, the platform can integrate the protection, measurement and control of the high-low voltage switch on the ground and off the ground, the implementation of the underground unmanned operation, the monitoring of the running state of the whole mine power system, the monitoring system of the operation parameters of the whole mine power system, and the monitoring system of the mine are realized, and the interconnection of the power system of the monitoring system of the coal mine is realized.
For example, china patent discloses a coal mine area electric network high-voltage leakage monitoring and fault positioning system, CN116643206A, which comprises a coal mine full-electric network high-voltage leakage monitoring system and a coal mine full-electric network high-voltage leakage fault positioning system, wherein the coal mine full-electric network high-voltage leakage monitoring system comprises an image acquisition unit, an image analysis unit, a gas acquisition unit, a gas analysis unit and a data transmission unit; the image acquisition unit is used for carrying out real-time monitoring and video image acquisition processing on all power grids of the coal mine area. The invention can not only monitor and process the line in the mine area in real time, but also effectively and rapidly reduce the investigation range when the line has leakage fault, and accurately locate the fault point of the leakage, thereby improving the effect and efficiency of monitoring the high-voltage leakage of the full power grid of the coal mine and locating the fault, improving the maintenance and replacement efficiency of maintenance personnel and avoiding the influence of the full power grid on the work of other normal lines.
Although the above scheme has the advantages, the traditional coal mine leakage monitoring and fault positioning system is limited to the sensor data of the power equipment, lacks collection and comprehensive analysis of other important data of the coal mine environment, has single data source and lacks intelligent technical support, limits comprehensive monitoring and management of the running state of the system, is easy to cause abnormal running and faults, cannot timely and accurately find hidden trouble, causes delay and increase of risks of fault treatment, affects the safety production and the operation efficiency of the coal mine, and therefore, a coal mine area electric network high-voltage leakage monitoring and fault positioning system is needed to solve the problems.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a high-voltage electric leakage monitoring and fault positioning system for a coal mine area power grid, which solves the problems of the prior art that the acquisition and comprehensive analysis of other important data of a coal mine environment are lacking, a single data source is lacking and the intelligent technical support is lacking, and the comprehensive monitoring and management of the running state of the system are limited.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
the invention provides a high-voltage leakage monitoring and fault positioning system for a coal mine area power grid, which comprises the following components:
The data processing module is used for collecting data from a plurality of sources and preprocessing the data, the data processing module comprises a data collecting unit and a data preprocessing unit, the data collecting unit is responsible for collecting data from a plurality of sources, the data collecting unit comprises power equipment sensor data, environment sensor data and equipment operation data, and the data preprocessing unit is used for cleaning, denoising and outlier processing of the collected original data;
The fusion analysis module is used for carrying out fusion analysis on the multi-source data and extracting key features to support fault diagnosis and prediction, and comprises a multi-source data fusion unit and a feature extraction unit, wherein the multi-source data fusion unit fuses the data from different sources to construct a fused system data set, and the feature extraction unit analyzes the fused data and extracts key features;
The fault diagnosis module is used for carrying out fault diagnosis and prediction based on data analysis, and comprises a data-driven fault diagnosis unit and a fault prediction and early warning unit, wherein the data-driven fault diagnosis unit carries out fault diagnosis by adopting a deep learning LSTM model based on data analysis results, judges abnormal states of the system, and predicts possible faults and timely sends early warning based on historical data and current trends;
The system comprises a dual-ecological system module, a real-time data feedback module and a state feedback module, wherein the dual-ecological system module is used for carrying out digital description and state feedback on an entity system and comprises a system digital unit and a state feedback unit, the system digital unit is a dual-ecological system model and is used for carrying out digital description on the entity system and providing comprehensive monitoring and management on the system, and the state feedback unit carries out state evaluation and adjustment on the digital system through real-time data feedback;
the decision support module is used for providing intelligent decision support and optimization suggestions and providing the intelligent decision support and optimization suggestions based on the system analysis result and the user requirements.
The invention is further arranged to: the monitored data in the data processing module comprises:
High-voltage line voltage, high-voltage line current, transformer temperature, high-voltage transformer humidity, switch on-off state and operation times, high-voltage line zero-sequence current change, leakage detector alarm signals and leakage quantity, coal mine environment temperature, humidity, air pressure, wind speed, power equipment running state and load condition, and switch tripping condition;
the invention is further arranged to: in the multi-source data fusion unit, the step of data fusion comprises the following steps:
Aiming at a high-voltage leakage monitoring scene, data from different sources are aligned in time, and the time alignment mode is as follows: Wherein Represent the firstThe time point at which the time point is the same,Representing a time interval;
Spatially aligning the sensor position data: wherein, the method comprises the steps of, wherein, Represent the firstData point and the firstThe spatial distance between the data points is such that,AndRespectively representing the spatial coordinates of two data points;
Then cleaning the data, and cleaning the cleaned data The method comprises the following steps: Here, the number of the parts of the device, here, The median of the data is represented and,Representing the absolute mid-bit difference of the data,To adjust parameters;
Then fusing the data features from different sources to generate feature vectors;
The invention is further arranged to: the step of extracting key features by the feature extraction unit comprises the following steps:
the high-dimensional data is reduced to a low-dimensional space, key features are reserved, Wherein, the method comprises the steps of, wherein,Is a matrix of raw data that is to be processed,Is a projection matrix which is a projection matrix,Is a data matrix after dimension reduction;
Calculating the correlation between the feature and the target variable, and selecting the feature with higher correlation with the target: wherein, the method comprises the steps of, wherein, AndRespectively represent samplesIs provided with a pair of the two characteristics,AndRespectively represent characteristics ofAndIs the average value of (2);
the invention is further arranged to: the step of extracting key features by the feature extraction unit further comprises the following steps:
Then, wavelet transformation is adopted to extract the frequency domain and time domain characteristics of the signals: wherein, the method comprises the steps of, wherein, In order to input a signal to the device,Is a function of the wavelet,As a result of the wavelet coefficients,AndIs the scale and translation parameter of the device,For indicating the change in time of the signalFor representing the variation of the wavelet function at different frequencies;
combining the original features to generate high-order features: ， namely the generated polynomial characteristic matrix;
The invention is further arranged to: in the data driving fault diagnosis unit, the fault diagnosis method comprises the following steps:
collecting time sequence data from a coal mine full power grid monitoring system, wherein the time sequence data comprises key characteristic data extracted from a fusion analysis module, and dividing the coal mine full power grid monitoring data into a test set and a training set;
Establishing an LSTM model, training the LSTM model by using the prepared data set, and optimizing by cross entropy loss function, wherein the loss function is defined as Expressed as: wherein, the method comprises the steps of, wherein, The parameters of the model are represented by the parameters,Representing the number of samples to be taken,The number of categories is indicated and,Representing a sampleBelongs to the category ofIs used for the identification of the tag of (c),Representing model versus sampleBelongs to the category ofIs used for predicting the probability of (1);
Evaluating the model by using an independent test data set, and then predicting new data by using a trained LSTM model to judge whether the system is in an abnormal state or not;
The invention is further arranged to: the fault prediction mode of the early warning unit adopts a GRU model, and specifically:
Collecting real-time monitoring data and partial data of the running state of the equipment in the historical data, retaining a time stamp for the data, and extracting relevant characteristics including the mean value, variance, peak value and harmonic content of current and voltage, and the running time and the temperature change rate of the equipment;
the invention is further arranged to: the GRU model specifically comprises the following components:
GRU model update door: ；
GRU model reset gate: ；
GRU model new state candidates: ；
GRU model hidden state update: ; wherein, To update the gate, the hidden state used to control the last time stepHow much information is retained and passed to the current time step；AndTo update the weight matrix of the gate, respectively for the current inputAnd the last hidden stateIs a linear transformation of (2); in order to update the bias term of the gate, Activating a function for Sigmoid;
to reset the gate for controlling the hidden state of the last time step For the current time stepIs used for the control of the (c),AndFor resetting the weight matrix of the gate, respectively for the current inputAnd the last hidden stateIs used for the linear transformation of (a),A bias term for the reset gate;
is a new state candidate value according to the current input And the last hidden stateThe calculated hidden state to be selected is calculated,Ensuring that the new state candidate value ranges from-1 to 1 for the hyperbolic tangent activation function;
for updating hidden state, for representing current time step Is a function of the information of (a),For element-by-element multiplication, combining the update gate and the new state candidate value, and calculating a final hidden state;
random gradient descent training is carried out on the selected GRU model by using historical data, and the current data is predicted by using the trained GRU model to obtain the probability and the category of fault occurrence;
the invention is further arranged to: the construction step of the dual-ecological system model comprises the following steps:
Extracting characteristics including mean value, variance and peak value of current and voltage, running time of equipment and temperature change rate from the preprocessed data by adopting sensor data of an entity system;
based on the selected characteristics, constructing a digital system description model, determining the structure and parameters of the model, and training the model;
Verifying the established digital system description model by using historical data, and evaluating the prediction performance and accuracy of the model;
establishing a real-time data feedback mechanism, and carrying out state evaluation and adjustment on the digital system through data acquired by the sensor in real time;
monitoring real-time data, and carrying out real-time analysis and diagnosis on the system state;
The invention is further arranged to: in the decision support module, the method for outputting the optimization suggestion comprises the following steps:
extracting key features from the historical data: the mean value, variance and peak value of the current and the voltage are used as input variables of the model;
constructing an intelligent decision support model by selecting a decision tree, a support vector machine and a neural network;
Training and optimizing the constructed model by utilizing historical data, analyzing and predicting real-time data by utilizing the constructed intelligent model, and identifying potential faults and abnormal conditions;
Based on the analysis results, the risk and impact of different decision schemes are evaluated, and targeted maintenance and optimization strategies are recommended.
Compared with the prior art, the invention has the following beneficial effects:
The invention deploys sensors for collecting high-voltage circuits, transformers and switching equipment, and detects coal mine environment data, temperature, humidity and air pressure, equipment running states and load conditions, a fusion analysis module fuses data from different sources, a fused system data set is constructed, key features are extracted to support fault diagnosis and prediction, data integration is realized through time and space alignment, a basis is provided for subsequent analysis decision, in the aspect of fault diagnosis, a data-driven method is adopted, a deep learning technology LSTM model is combined, abnormal state diagnosis is carried out on the system, the abnormal state of the system can be accurately judged through training and verification of historical data, early warning can be timely sent out, in addition, a dual-ecological system module realizes entity system monitoring management through digital description and state feedback, a system digital unit constructs a digital system description model, the system state is evaluated and adjusted through a real-time data feedback mechanism, finally, a decision support module provides intelligent decision support and optimization advice based on system analysis results and user requirements, the feature extraction, model construction and optimization are adopted to predict faults, corresponding safety and optimization are carried out, and safety and operation advice are improved.
According to the invention, multiple data of power equipment, environment sensors and equipment operation data are collected and comprehensively analyzed by adopting multi-source data fusion, the power equipment, the environment sensors and the equipment operation data are not only dependent on power grid data, but also combined with other data sources, the environment sensor data and the equipment operation data are used for constructing a multi-dimensional fault diagnosis model, so that the accuracy and the comprehensiveness of system diagnosis are improved, meanwhile, the LSTM model and the GRU model are deeply learned, the accuracy and the efficiency of fault diagnosis are improved, the abnormal state of the system can be more accurately judged, potential faults can be timely early warned and processed, a real-time data feedback mechanism is built, the system state can be evaluated and adjusted in real time, and the response speed and the fault processing efficiency of the system are greatly improved.
Drawings
FIG. 1 is a diagram of a system for monitoring high voltage leakage and locating faults in a coal mine area power network according to the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The invention is described in further detail below with reference to the attached drawing figures:
Examples
Referring to fig. 1, the present invention provides a system for monitoring high voltage leakage and positioning faults of a power network in a coal mine area, comprising:
The data processing module is used for collecting data from a plurality of sources and preprocessing the data, the data processing module comprises a data collecting unit and a data preprocessing unit, the data collecting unit is responsible for collecting data from a plurality of sources, the data comprises power equipment sensor data, environment sensor data and equipment operation data, and the data preprocessing unit is used for cleaning, denoising and outlier processing of the collected original data;
The monitored data in the data processing module includes:
High-voltage line voltage, high-voltage line current, transformer temperature, high-voltage transformer humidity, switch on-off state and operation times, high-voltage line zero-sequence current change, leakage detector alarm signals and leakage quantity, coal mine environment temperature, humidity, air pressure, wind speed, power equipment running state and load condition, and switch tripping condition;
The fusion analysis module is used for carrying out fusion analysis on the multi-source data and extracting key features to support fault diagnosis and prediction, and comprises a multi-source data fusion unit and a feature extraction unit, wherein the multi-source data fusion unit fuses the data from different sources to construct a fused system data set to support comprehensive analysis and decision, and the feature extraction unit analyzes the fused data to extract key features and provide support for fault diagnosis and prediction;
In the multi-source data fusion unit, the data fusion step comprises the following steps:
Aiming at a high-voltage leakage monitoring scene, data from different sources are aligned in time, and the time alignment mode is as follows: Wherein Represent the firstThe time point at which the time point is the same,Representing a time interval;
Spatially aligning the sensor position data: wherein, the method comprises the steps of, wherein, Represent the firstData point and the firstThe spatial distance between the data points is such that,AndRespectively representing the spatial coordinates of two data points;
Then cleaning the data, and cleaning the cleaned data The method comprises the following steps: Here, the number of the parts of the device, here, The median of the data is represented and,Representing the absolute mid-bit difference of the data,To adjust parameters;
Then fusing the data features from different sources to generate feature vectors;
Through data fusion, data from different sources are effectively fused, and a more complete and accurate system data set is constructed;
the key feature extraction step performed by the feature extraction unit comprises the following steps:
the high-dimensional data is reduced to a low-dimensional space, key features are reserved, Wherein, the method comprises the steps of, wherein,Is a matrix of raw data that is to be processed,Is a projection matrix which is a projection matrix,Is a data matrix after dimension reduction;
Calculating the correlation between the feature and the target variable, and selecting the feature with higher correlation with the target: wherein, the method comprises the steps of, wherein, AndRespectively represent samplesIs provided with a pair of the two characteristics,AndRespectively represent characteristics ofAndIs the average value of (2);
The step of extracting key features by the feature extraction unit further comprises:
Then, wavelet transformation is adopted to extract the frequency domain and time domain characteristics of the signals: wherein, the method comprises the steps of, wherein, In order to input a signal to the device,Is a function of the wavelet,As a result of the wavelet coefficients,AndIs the scale and translation parameter of the device,For indicating the change in time of the signalFor representing the variation of the wavelet function at different frequencies;
combining the original features to generate high-order features: ， namely the generated polynomial characteristic matrix;
Extracting key features from the fused data through key feature extraction, and providing support for subsequent fault diagnosis and prediction;
The fault diagnosis module is used for carrying out fault diagnosis and prediction based on data analysis, and comprises a data-driven fault diagnosis unit, a fault prediction and early warning unit and a data-driven fault diagnosis unit, wherein the data-driven fault diagnosis unit is used for carrying out fault diagnosis based on data analysis results by adopting a deep learning LSTM model, judging abnormal states of the system, and the fault prediction and early warning unit is used for predicting possible faults based on historical data and current trends, timely giving early warning and taking measures in advance to prevent risks;
in the data driving fault diagnosis unit, the fault diagnosis method comprises the following steps:
collecting time sequence data from a coal mine full power grid monitoring system, wherein the time sequence data comprises key characteristic data extracted from a fusion analysis module, and dividing the coal mine full power grid monitoring data into a test set and a training set;
Establishing an LSTM model, training the LSTM model by using the prepared data set, and optimizing by cross entropy loss function, wherein the loss function is defined as Expressed as: wherein, the method comprises the steps of, wherein, The parameters of the model are represented by the parameters,Representing the number of samples to be taken,The number of categories is indicated and,Representing a sampleBelongs to the category ofIs used for the identification of the tag of (c),Representing model versus sampleBelongs to the category ofIs used for predicting the probability of (1);
Evaluating the model by using an independent test data set, and then predicting new data by using a trained LSTM model to judge whether the system is in an abnormal state or not;
the fault prediction mode of the fault prediction unit adopts a GRU model, and specifically:
Collecting real-time monitoring data and partial data of the running state of the equipment in the historical data, retaining a time stamp for the data, and extracting relevant characteristics including the mean value, variance, peak value and harmonic content of current and voltage, and the running time and the temperature change rate of the equipment;
the GRU model is specifically as follows:
GRU model update door: ；
GRU model reset gate: ；
GRU model new state candidates: ；
GRU model hidden state update: ; wherein, To update the gate, the hidden state used to control the last time stepHow much information is retained and passed to the current time step；AndTo update the weight matrix of the gate, respectively for the current inputAnd the last hidden stateIs a linear transformation of (2); in order to update the bias term of the gate, Activating a function for Sigmoid;
to reset the gate for controlling the hidden state of the last time step For the current time stepIs used for the control of the (c),AndFor resetting the weight matrix of the gate, respectively for the current inputAnd the last hidden stateIs used for the linear transformation of (a),A bias term for the reset gate;
is a new state candidate value according to the current input And the last hidden stateThe calculated hidden state to be selected is calculated,Ensuring that the new state candidate value ranges from-1 to 1 for the hyperbolic tangent activation function;
for updating hidden state, for representing current time step Is a function of the information of (a),For element-by-element multiplication, combining the update gate and the new state candidate value, and calculating a final hidden state;
random gradient descent training is carried out on the selected GRU model by using historical data, and the current data is predicted by using the trained GRU model to obtain the probability and the category of fault occurrence;
The GRU model is used for fault prediction and early warning, so that historical data and current trends can be better utilized, potential faults can be found in advance, and corresponding preventive measures are taken;
The system comprises a dual ecological system module, a real-time data feedback module and a control module, wherein the dual ecological system module is used for carrying out digital description and state feedback on an entity system and comprises a system digital unit and a state feedback unit, the system digital unit is a dual ecological system model and is used for carrying out digital description on the entity system, providing comprehensive monitoring and management on the system, and the state feedback unit carries out state evaluation and adjustment on the digital system through real-time data feedback so as to ensure the normal operation of the system;
The construction step of the dual-ecological system model comprises the following steps:
Extracting characteristics including mean value, variance and peak value of current and voltage, running time of equipment and temperature change rate from the preprocessed data by adopting sensor data of an entity system;
based on the selected characteristics, constructing a digital system description model, determining the structure and parameters of the model, and training the model;
Verifying the established digital system description model by using historical data, and evaluating the prediction performance and accuracy of the model;
establishing a real-time data feedback mechanism, and carrying out state evaluation and adjustment on the digital system through data acquired by the sensor in real time;
monitoring real-time data, and carrying out real-time analysis and diagnosis on the system state;
The decision support module is used for providing intelligent decision support and optimization suggestions and helping a user to make scientific decisions based on a system analysis result and user requirements;
in the decision support module, the output optimization suggestion method comprises the following steps:
extracting key features from the historical data: the mean value, variance and peak value of the current and the voltage are used as input variables of the model;
constructing an intelligent decision support model by selecting a decision tree, a support vector machine and a neural network;
Training and optimizing the constructed model by utilizing historical data, analyzing and predicting real-time data by utilizing the constructed intelligent model, and identifying potential faults and abnormal conditions;
Based on the analysis result, evaluating the risks and influences of different decision schemes, recommending targeted maintenance and optimization strategies so as to reduce the system risks and improve the operation efficiency;
the decision support module analyzes the system state more comprehensively and accurately, provides intelligent decision support and optimization suggestions, helps users to make scientific decisions, and improves the operation efficiency and safety of the system.
The invention deploys sensors for collecting high-voltage circuits, transformers and switching equipment, and detects coal mine environment data, temperature, humidity and air pressure, equipment running states and load conditions, a fusion analysis module fuses data from different sources, a fused system data set is constructed, key features are extracted to support fault diagnosis and prediction, data integration is realized through time and space alignment, a basis is provided for subsequent analysis decision, in the aspect of fault diagnosis, a data-driven method is adopted, a deep learning technology LSTM model is combined, abnormal state diagnosis is carried out on the system, the abnormal state of the system can be accurately judged through training and verification of historical data, early warning can be timely sent out, in addition, a dual-ecological system module realizes entity system monitoring management through digital description and state feedback, a system digital unit constructs a digital system description model, the system state is evaluated and adjusted through a real-time data feedback mechanism, finally, a decision support module provides intelligent decision support and optimization advice based on system analysis results and user requirements, the feature extraction, model construction and optimization are adopted to predict faults, corresponding safety and optimization are carried out, and safety and operation advice are improved.
According to the invention, multiple data of power equipment, environment sensors and equipment operation data are collected and comprehensively analyzed by adopting multi-source data fusion, the power equipment, the environment sensors and the equipment operation data are not only dependent on power grid data, but also combined with other data sources, the environment sensor data and the equipment operation data are used for constructing a multi-dimensional fault diagnosis model, so that the accuracy and the comprehensiveness of system diagnosis are improved, meanwhile, the LSTM model and the GRU model are deeply learned, the accuracy and the efficiency of fault diagnosis are improved, the abnormal state of the system can be more accurately judged, potential faults can be timely early warned and processed, a real-time data feedback mechanism is built, the system state can be evaluated and adjusted in real time, and the response speed and the fault processing efficiency of the system are greatly improved.
The above is only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited by this, and any modification made on the basis of the technical scheme according to the technical idea of the present invention falls within the protection scope of the claims of the present invention.
Claims (10)
1. The utility model provides a colliery district electric network high voltage electric leakage control and fault location system which characterized in that includes:
The data processing module is used for collecting data from a plurality of sources and preprocessing the data, the data processing module comprises a data collecting unit and a data preprocessing unit, the data collecting unit is responsible for collecting data from a plurality of sources, the data collecting unit comprises power equipment sensor data, environment sensor data and equipment operation data, and the data preprocessing unit is used for cleaning, denoising and outlier processing of the collected original data;
The fusion analysis module is used for carrying out fusion analysis on the multi-source data and extracting key features to support fault diagnosis and prediction, and comprises a multi-source data fusion unit and a feature extraction unit, wherein the multi-source data fusion unit fuses the data from different sources to construct a fused system data set, and the feature extraction unit analyzes the fused data and extracts key features;
The fault diagnosis module is used for carrying out fault diagnosis and prediction based on data analysis, and comprises a data-driven fault diagnosis unit and a fault prediction and early warning unit, wherein the data-driven fault diagnosis unit carries out fault diagnosis by adopting a deep learning LSTM model based on data analysis results, judges abnormal states of the system, and predicts possible faults and timely sends early warning based on historical data and current trends;
The system comprises a dual-ecological system module, a real-time data feedback module and a state feedback module, wherein the dual-ecological system module is used for carrying out digital description and state feedback on an entity system and comprises a system digital unit and a state feedback unit, the system digital unit is a dual-ecological system model and is used for carrying out digital description on the entity system and providing comprehensive monitoring and management on the system, and the state feedback unit carries out state evaluation and adjustment on the digital system through real-time data feedback;
the decision support module is used for providing intelligent decision support and optimization suggestions and providing the intelligent decision support and optimization suggestions based on the system analysis result and the user requirements.
2. The system for monitoring and locating high voltage leakage of a coal mine area power network according to claim 1, wherein the monitored data in the data processing module comprises:
high-voltage line voltage, high-voltage line current, transformer temperature, high-voltage transformer humidity, switch on-off state and operation times, high-voltage line zero-sequence current change, leakage detector alarm signals and leakage quantity, coal mine environment temperature, humidity, air pressure, air speed, operation state and load condition of power equipment and switch tripping condition.
3. The system for monitoring and positioning high-voltage leakage of a power network in a coal mine area according to claim 2, wherein the step of performing data fusion in the multi-source data fusion unit comprises:
Aiming at a high-voltage leakage monitoring scene, data from different sources are aligned in time, and the time alignment mode is as follows: Wherein Represent the firstThe time point at which the time point is the same,Representing a time interval;
Spatially aligning the sensor position data: wherein, the method comprises the steps of, wherein, Represent the firstData point and the firstThe spatial distance between the data points is such that,AndRespectively representing the spatial coordinates of two data points;
Then cleaning the data, and cleaning the cleaned data The method comprises the following steps: Here, the number of the parts of the device, here, The median of the data is represented and,Representing the absolute mid-bit difference of the data,To adjust parameters;
And then fusing the data features from different sources to generate feature vectors.
4. A coal mine area power grid high voltage leakage monitoring and fault locating system according to claim 3 wherein the feature extraction unit performs the key feature extraction step comprising:
the high-dimensional data is reduced to a low-dimensional space, key features are reserved, Wherein, the method comprises the steps of, wherein,Is a matrix of raw data that is to be processed,Is a projection matrix which is a projection matrix,Is a data matrix after dimension reduction;
Calculating the correlation between the feature and the target variable, and selecting the feature with higher correlation with the target: wherein, the method comprises the steps of, wherein, AndRespectively represent samplesIs provided with a pair of the two characteristics,AndRespectively represent characteristics ofAndIs a mean value of (c).
5. The system for monitoring and locating high voltage leakage of power network in coal mine area according to claim 4, wherein the step of extracting key features by the feature extracting unit further comprises:
Then, wavelet transformation is adopted to extract the frequency domain and time domain characteristics of the signals: wherein, the method comprises the steps of, wherein, In order to input a signal to the device,Is a function of the wavelet,As a result of the wavelet coefficients,AndIs the scale and translation parameter of the device,For indicating the change in time of the signalFor representing the variation of the wavelet function at different frequencies;
combining the original features to generate high-order features: ， I.e. the generated polynomial feature matrix.
6. The system for monitoring and positioning high-voltage leakage of a power network in a coal mine area according to claim 5, wherein the data driving fault diagnosis unit performs a fault diagnosis method comprising:
collecting time sequence data from a coal mine full power grid monitoring system, wherein the time sequence data comprises key characteristic data extracted from a fusion analysis module, and dividing the coal mine full power grid monitoring data into a test set and a training set;
Establishing an LSTM model, training the LSTM model by using the prepared data set, and optimizing by cross entropy loss function, wherein the loss function is defined as Expressed as: wherein, the method comprises the steps of, wherein, The parameters of the model are represented by the parameters,Representing the number of samples to be taken,The number of categories is indicated and,Representing a sampleBelongs to the category ofIs used for the identification of the tag of (c),Representing model versus sampleBelongs to the category ofIs used for predicting the probability of (1);
And evaluating the model by using an independent test data set, and then predicting new data by using a trained LSTM model to judge whether the system is in an abnormal state.
7. The system for monitoring and positioning high-voltage leakage of a coal mine area power grid according to claim 6, wherein the fault prediction and early warning unit adopts a GRU model in a fault prediction mode, and specifically:
And collecting part of data of real-time monitoring data and equipment operation states in historical data, retaining a time stamp for the data, and extracting relevant characteristics including mean value, variance, peak value and harmonic content of current and voltage, equipment operation time and temperature change rate.
8. The coal mine area power grid high voltage leakage monitoring and fault locating system according to claim 7, wherein the GRU model is specifically:
GRU model update door: ；
GRU model reset gate: ；
GRU model new state candidates: ；
GRU model hidden state update: ; wherein, To update the gate, the hidden state used to control the last time stepHow much information is retained and passed to the current time step；AndTo update the weight matrix of the gate, respectively for the current inputAnd the last hidden stateIs a linear transformation of (2); in order to update the bias term of the gate, Activating a function for Sigmoid;
to reset the gate for controlling the hidden state of the last time step For the current time stepIs used for the control of the (c),AndFor resetting the weight matrix of the gate, respectively for the current inputAnd the last hidden stateIs used for the linear transformation of (a),A bias term for the reset gate;
is a new state candidate value according to the current input And the last hidden stateThe calculated hidden state to be selected is calculated,Ensuring that the new state candidate value ranges from-1 to 1 for the hyperbolic tangent activation function;
for updating hidden state, for representing current time step Is a function of the information of (a),For element-by-element multiplication, combining the update gate and the new state candidate value, and calculating a final hidden state;
And carrying out random gradient descent training on the selected GRU model by using historical data, and predicting the current data by using the trained GRU model to obtain the probability and the category of fault occurrence.
9. The coal mine area power grid high voltage leakage monitoring and fault locating system according to claim 8, wherein the dual ecological system model building step comprises:
Extracting characteristics including mean value, variance and peak value of current and voltage, running time of equipment and temperature change rate from the preprocessed data by adopting sensor data of an entity system;
based on the selected characteristics, constructing a digital system description model, determining the structure and parameters of the model, and training the model;
Verifying the established digital system description model by using historical data, and evaluating the prediction performance and accuracy of the model;
establishing a real-time data feedback mechanism, and carrying out state evaluation and adjustment on the digital system through data acquired by the sensor in real time;
and monitoring the real-time data, and carrying out real-time analysis and diagnosis on the system state.
10. The system for monitoring and positioning high-voltage leakage of a power grid in a coal mine area according to claim 9, wherein the decision support module outputs an optimization suggestion method comprising:
extracting key features from the historical data: the mean value, variance and peak value of the current and the voltage are used as input variables of the model;
constructing an intelligent decision support model by selecting a decision tree, a support vector machine and a neural network;
Training and optimizing the constructed model by utilizing historical data, analyzing and predicting real-time data by utilizing the constructed intelligent model, and identifying potential faults and abnormal conditions;
Based on the analysis results, the risk and impact of different decision schemes are evaluated, and targeted maintenance and optimization strategies are recommended.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410453745.7A CN118409157A (en) | 2024-04-16 | 2024-04-16 | High voltage leakage monitoring and fault location system for coal mining area power grid |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410453745.7A CN118409157A (en) | 2024-04-16 | 2024-04-16 | High voltage leakage monitoring and fault location system for coal mining area power grid |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118409157A true CN118409157A (en) | 2024-07-30 |
Family
ID=91982337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410453745.7A Pending CN118409157A (en) | 2024-04-16 | 2024-04-16 | High voltage leakage monitoring and fault location system for coal mining area power grid |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118409157A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118659536A (en) * | 2024-08-16 | 2024-09-17 | 中建安装集团有限公司 | Intelligent control system and method for construction electricity consumption based on multimodal data integration |
| CN118687632A (en) * | 2024-08-28 | 2024-09-24 | 山东理工职业学院 | A coal mine electromechanical equipment operating status monitoring system based on data analysis |
| CN118839141A (en) * | 2024-09-20 | 2024-10-25 | 国网河南省电力公司新乡供电公司 | Power equipment fault monitoring method based on edge calculation |
| CN118861869A (en) * | 2024-09-23 | 2024-10-29 | 中国电建集团山东电力建设第一工程有限公司 | A cable fault prediction method and system introducing uncertain factors |
| CN118859037A (en) * | 2024-09-23 | 2024-10-29 | 国网河南省电力公司新乡供电公司 | A method for power equipment fault analysis based on multi-source data fusion |
| CN119130441A (en) * | 2024-09-18 | 2024-12-13 | 广州南网科研技术有限责任公司 | A circuit safety management method based on low-voltage safety comprehensive protection module of IoT |
| CN119337189A (en) * | 2024-12-19 | 2025-01-21 | 华夏天信智能物联股份有限公司 | A method and device for monitoring miner behavior |
| CN119483502A (en) * | 2024-10-29 | 2025-02-18 | 中城远大能源有限公司 | A photovoltaic power station monitoring system |
| CN119513755A (en) * | 2024-10-21 | 2025-02-25 | 广州有电信息科技有限公司 | Inspection and management method of distribution network |
| CN119760617A (en) * | 2025-03-06 | 2025-04-04 | 山东科技大学 | A comprehensive monitoring method and system for underground coal mine pressure based on Internet of Things |
| CN119881544A (en) * | 2025-03-27 | 2025-04-25 | 福建闽高电力能源集团有限公司 | Smart power grid fault positioning method and device |
| CN119884700A (en) * | 2024-11-27 | 2025-04-25 | 广西电网有限责任公司 | Smart power grid monitoring and alarming method and system |
| CN120044430A (en) * | 2024-11-21 | 2025-05-27 | 国网山东省电力公司烟台供电公司 | Online monitoring system and method for leakage current and insulation state of power distribution network cable |
| CN120073628A (en) * | 2025-04-28 | 2025-05-30 | 广东电网有限责任公司阳江供电局 | Power grid fault isolation method and isolation system |
| CN120416443A (en) * | 2025-07-07 | 2025-08-01 | 济南辰阳信息技术有限公司 | A video monitoring method for underground coal mines |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102008472B1 (en) * | 2018-12-19 | 2019-08-07 | (주)대신피아이씨 | Real Time Remote Management and Alarm Call out System of Electrical Consumers Type based on IoT |
| US20200387785A1 (en) * | 2019-06-05 | 2020-12-10 | Wuhan University | Power equipment fault detecting and positioning method of artificial intelligence inference fusion |
| CN113394745A (en) * | 2021-06-30 | 2021-09-14 | 济源职业技术学院 | Selective leakage protection system for underground high-voltage power grid of coal mine |
| KR102325098B1 (en) * | 2020-11-09 | 2021-11-11 | (주)큐센텍 | Short circuit break device and remote power control system having thereof |
| CN114089088A (en) * | 2020-07-15 | 2022-02-25 | 北京天阳睿博科技有限公司 | Whole coal mine grid high-voltage electric leakage monitoring system based on wams and Internet of things technology |
| WO2023142424A1 (en) * | 2022-01-25 | 2023-08-03 | 国网江苏省电力有限公司南京供电分公司 | Power financial service risk control method and system based on gru-lstm neural network |
| CN116643206A (en) * | 2023-07-27 | 2023-08-25 | 北京天阳睿博科技有限公司 | High-voltage leakage monitoring and fault location system for the whole power grid of coal mine |
| CN117251812A (en) * | 2023-09-22 | 2023-12-19 | 河南博兆电子科技有限公司 | A high-voltage power line operation fault detection method based on big data analysis |
| CN117706284A (en) * | 2023-10-31 | 2024-03-15 | 贵州电网有限责任公司 | Substation primary equipment discharge early warning detection method and system |
| CN117853084A (en) * | 2023-11-20 | 2024-04-09 | 淮北矿业股份有限公司 | Remote fault diagnosis method of main hoisting system based on AI and mechanism fusion |
| CN117874467A (en) * | 2024-01-26 | 2024-04-12 | 沈阳工程学院 | Power equipment state monitoring method and system based on multi-source data fusion |
| CN117992896A (en) * | 2024-04-03 | 2024-05-07 | 北京天阳睿博科技有限公司 | High voltage power supply fault location and line selection system in coal mining areas |
-
2024
- 2024-04-16 CN CN202410453745.7A patent/CN118409157A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102008472B1 (en) * | 2018-12-19 | 2019-08-07 | (주)대신피아이씨 | Real Time Remote Management and Alarm Call out System of Electrical Consumers Type based on IoT |
| US20200387785A1 (en) * | 2019-06-05 | 2020-12-10 | Wuhan University | Power equipment fault detecting and positioning method of artificial intelligence inference fusion |
| CN114089088A (en) * | 2020-07-15 | 2022-02-25 | 北京天阳睿博科技有限公司 | Whole coal mine grid high-voltage electric leakage monitoring system based on wams and Internet of things technology |
| KR102325098B1 (en) * | 2020-11-09 | 2021-11-11 | (주)큐센텍 | Short circuit break device and remote power control system having thereof |
| CN113394745A (en) * | 2021-06-30 | 2021-09-14 | 济源职业技术学院 | Selective leakage protection system for underground high-voltage power grid of coal mine |
| WO2023142424A1 (en) * | 2022-01-25 | 2023-08-03 | 国网江苏省电力有限公司南京供电分公司 | Power financial service risk control method and system based on gru-lstm neural network |
| CN116643206A (en) * | 2023-07-27 | 2023-08-25 | 北京天阳睿博科技有限公司 | High-voltage leakage monitoring and fault location system for the whole power grid of coal mine |
| CN117251812A (en) * | 2023-09-22 | 2023-12-19 | 河南博兆电子科技有限公司 | A high-voltage power line operation fault detection method based on big data analysis |
| CN117706284A (en) * | 2023-10-31 | 2024-03-15 | 贵州电网有限责任公司 | Substation primary equipment discharge early warning detection method and system |
| CN117853084A (en) * | 2023-11-20 | 2024-04-09 | 淮北矿业股份有限公司 | Remote fault diagnosis method of main hoisting system based on AI and mechanism fusion |
| CN117874467A (en) * | 2024-01-26 | 2024-04-12 | 沈阳工程学院 | Power equipment state monitoring method and system based on multi-source data fusion |
| CN117992896A (en) * | 2024-04-03 | 2024-05-07 | 北京天阳睿博科技有限公司 | High voltage power supply fault location and line selection system in coal mining areas |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118659536A (en) * | 2024-08-16 | 2024-09-17 | 中建安装集团有限公司 | Intelligent control system and method for construction electricity consumption based on multimodal data integration |
| CN118687632A (en) * | 2024-08-28 | 2024-09-24 | 山东理工职业学院 | A coal mine electromechanical equipment operating status monitoring system based on data analysis |
| CN119130441A (en) * | 2024-09-18 | 2024-12-13 | 广州南网科研技术有限责任公司 | A circuit safety management method based on low-voltage safety comprehensive protection module of IoT |
| CN118839141A (en) * | 2024-09-20 | 2024-10-25 | 国网河南省电力公司新乡供电公司 | Power equipment fault monitoring method based on edge calculation |
| CN118861869A (en) * | 2024-09-23 | 2024-10-29 | 中国电建集团山东电力建设第一工程有限公司 | A cable fault prediction method and system introducing uncertain factors |
| CN118859037A (en) * | 2024-09-23 | 2024-10-29 | 国网河南省电力公司新乡供电公司 | A method for power equipment fault analysis based on multi-source data fusion |
| CN119513755A (en) * | 2024-10-21 | 2025-02-25 | 广州有电信息科技有限公司 | Inspection and management method of distribution network |
| CN119483502A (en) * | 2024-10-29 | 2025-02-18 | 中城远大能源有限公司 | A photovoltaic power station monitoring system |
| CN120044430A (en) * | 2024-11-21 | 2025-05-27 | 国网山东省电力公司烟台供电公司 | Online monitoring system and method for leakage current and insulation state of power distribution network cable |
| CN119884700A (en) * | 2024-11-27 | 2025-04-25 | 广西电网有限责任公司 | Smart power grid monitoring and alarming method and system |
| CN119337189A (en) * | 2024-12-19 | 2025-01-21 | 华夏天信智能物联股份有限公司 | A method and device for monitoring miner behavior |
| CN119760617A (en) * | 2025-03-06 | 2025-04-04 | 山东科技大学 | A comprehensive monitoring method and system for underground coal mine pressure based on Internet of Things |
| CN119881544A (en) * | 2025-03-27 | 2025-04-25 | 福建闽高电力能源集团有限公司 | Smart power grid fault positioning method and device |
| CN120073628A (en) * | 2025-04-28 | 2025-05-30 | 广东电网有限责任公司阳江供电局 | Power grid fault isolation method and isolation system |
| CN120416443A (en) * | 2025-07-07 | 2025-08-01 | 济南辰阳信息技术有限公司 | A video monitoring method for underground coal mines |
| CN120416443B (en) * | 2025-07-07 | 2025-09-05 | 济南辰阳信息技术有限公司 | A video monitoring method for underground coal mines |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118409157A (en) | High voltage leakage monitoring and fault location system for coal mining area power grid | |
| CN120074026B (en) | Full-dimensional real-time monitoring stable operation linkage system of power system | |
| CN117612345A (en) | A power equipment status monitoring and alarm system and method | |
| CN105203876B (en) | It is a kind of to utilize support vector machines and the transformer online monitoring state evaluating method of correlation analysis | |
| CN110095661B (en) | Distribution transformer high-voltage side open-phase fault first-aid repair method | |
| CN117639228A (en) | Distribution network operating status prediction method and system based on digital twins | |
| CN117992896A (en) | High voltage power supply fault location and line selection system in coal mining areas | |
| CN114091549A (en) | Equipment fault diagnosis method based on deep residual error network | |
| CN113763667A (en) | A fire early warning and state monitoring device and method based on 5G edge computing | |
| CN120142835A (en) | An intelligent diagnosis system for a self-diagnostic switch device for distribution network faults | |
| CN119813201B (en) | Adaptive reclosing optimization method and system for power distribution network | |
| CN117409529A (en) | A multi-scenario electrical fire online monitoring method and system | |
| CN120490784A (en) | Digital twinning-based vacuum circuit breaker state online monitoring method and system | |
| CN118038295A (en) | Real-time online identification system for defects of power transmission line | |
| CN118336911A (en) | An online monitoring fault diagnosis system and method based on physical model | |
| CN114548209B (en) | A power grid strong correlation fault analysis system and method based on power flow fingerprint spectrum | |
| CN120709928A (en) | Distribution network protection setting decision system and method based on big data | |
| CN119293713A (en) | A method for anomaly detection and automatic positioning based on data curve | |
| CN104317778A (en) | Massive monitoring data based substation equipment fault diagnosis method | |
| CN120334680B (en) | Power grid digital twin fault simulation equipment reconstructed from historical data | |
| CN117094705A (en) | A method, system and equipment applied to high-voltage switchgear defect prediction | |
| CN116961215A (en) | A quick response and processing method for power system faults | |
| CN116796261B (en) | Closed switch equipment mechanical characteristic prediction method based on artificial intelligence | |
| CN117494009A (en) | Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform | |
| Yuan et al. | A Health Status Assessment Method of Switchgear in Substation Based on Digital Twin Technology and Random Matrix Model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20240730 |
|
| WD01 | Invention patent application deemed withdrawn after publication |